Triple
T10782625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matt Moore |
E254363
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Mary Moore |
E336497
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Mary Moore | Statement: [Matt Moore, sibling, Mary Moore]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Moore Context triple: [Matt Moore, sibling, Mary Moore]
-
A.
Mary Moore
chosen
Mary Moore is the daughter of renowned British sculptor Henry Moore.
-
B.
Sandi Patty
Sandi Patty is an acclaimed American Christian music singer known for her powerful soprano voice and numerous Dove Awards.
-
C.
Carolyn McAfee
Carolyn McAfee is the namesake and likely a key benefactor or honoree of the James and Carolyn McAfee School of Theology at Mercer University.
-
D.
Anna Wise
Anna Wise is an American singer and songwriter best known for her ethereal vocals and frequent collaborations with Kendrick Lamar on critically acclaimed hip-hop projects.
-
E.
Betsy Garth
Betsy Garth is a central character in the Western television series "The Virginian," known for her close connection to the Shiloh Ranch and its core cast.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732c5618081908f72838ed42ed05c |
completed | April 9, 2026, 5:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de55fbfc70819098eb40cf0d1b9e8c |
completed | April 14, 2026, 2:58 p.m. |
Created at: April 8, 2026, 9:17 p.m.